Unsupervised Dimensionality Reduction Research Articles

Dimensionality reduction beyond neural subspaces with slice tensor component analysis.

Recent work has argued that large-scale neural recordings are often well described by patterns of coactivation across neurons. Yet the view that neural variability is constrained to a fixed, low-dimensional subspace may overlook higher-dimensional structure, including stereotyped neural sequences or slowly evolving latent spaces. Here we argue that task-relevant variability in neural data can also cofluctuate over trials or time, defining distinct 'covariability classes' that may co-occur within the same dataset. To demix these covariability classes, we develop sliceTCA (slice tensor component analysis), a new unsupervised dimensionality reduction method for neural data tensors. In three example datasets, including motor cortical activity during a classic reaching task in primates and recent multiregion recordings in mice, we show that sliceTCA can capture more task-relevant structure in neural data using fewer components than traditional methods. Overall, our theoretical framework extends the classic view of low-dimensional population activity by incorporating additional classes of latent variables capturing higher-dimensional structure.

Robust Principal Component Analysis via Joint Reconstruction and Projection.

Principal component analysis (PCA) is one of the most widely used unsupervised dimensionality reduction algorithms, but it is very sensitive to outliers because the squared l2 -norm is used as distance metric. Recently, many scholars have devoted themselves to solving this difficulty. They learn the projection matrix from minimum reconstruction error or maximum projection variance as the starting point, which leads them to ignore a serious problem, that is, the original PCA learns the projection matrix by minimizing the reconstruction error and maximizing the projection variance simultaneously, but they only consider one of them, which imposes various limitations on the performance of model. To solve this problem, we propose a novel robust principal component analysis via joint reconstruction and projection, namely, RPCA-RP, which combines reconstruction error and projection variance to fully mine the potential information of data. Furthermore, we carefully design a discrete weight for model to implicitly distinguish between normal data and outliers, so as to easily remove outliers and improve the robustness of method. In addition, we also unexpectedly discovered that our method has anomaly detection capabilities. Subsequently, an effective iterative algorithm is explored to solve this problem and perform related theoretical analysis. Extensive experimental results on several real-world datasets and RGB large-scale dataset demonstrate the superiority of our method.

Smart Circuit Design Machine Learning-Driven Optimization for Enhanced Performance in Electronics and Computer Engineering.

In the realm of Electronics and Computer engineering, achieving optimal performance of circuits amidst escalating complexity poses significant challenges. Traditional manual optimization techniques are often inadequate to navigate the intricacies of modern electronic systems. This paper advocates for the adoption of machine learning-driven optimization as a transformative approach to smart circuit design. By leveraging machine learning algorithms, engineers can systematically explore the expansive design space, discern complex relationships between circuit parameters and performance metrics, and ultimately enhance the efficiency and effectiveness of electronic circuits. This paper comprehensively reviews the application of machine learning techniques in circuit design optimization. Supervised learning algorithms such as neural networks, support vector machines, and decision trees enable the modeling of intricate interdependencies within electronic circuits. Unsupervised learning techniques, including clustering and dimensionality reduction, facilitate efficient exploration of the design landscape by identifying patterns and correlations. Additionally, reinforcement learning algorithms offer an autonomous approach to circuit optimization through iterative learning and refinement. Real-world applications of machine learning-driven optimization in electronics and computer engineering span various domains, including power-efficient integrated circuits, signal processing algorithm optimization, and layout optimization for enhanced performance and reliability. Moreover, machine learning techniques play a crucial role in mitigating variability in semiconductor manufacturing processes, ensuring robustness and reliability of electronic systems in the face of uncertainties. Despite the promising potential of machine learning in circuit design optimization, challenges such as dataset acquisition, model interpretability, and scalability to complex circuits persist. Addressing these challenges requires innovative research endeavors, including the development of hybrid optimization techniques and novel hardware architectures. DOI: https://doi.org/10.52783/tjjpt.v45.i02.6339

FETAL 3D-ECHO CLASSIFICATION AND SEGMENTATION USING COLOR AND TEXTURAL FEATURES FOR TR DETECTION

Tricuspid regurgitation (TR) is a condition in which the valve between the right atrium and right ventricle does not close properly. Therefore, blood leaks backward into the upper right chamber. Most commonly, tricuspid regurgitation is caused by an enlarged right ventricle. In this paper, a novel deep learning technique called Tricuspid regurgitation identification in the fetal heart (TRI-FH) approach has been proposed, for identifying TR in the early stages. The gathered 3D-echo images are pre-processed to improve the quality of the images. The feature extraction techniques namely color-level co-occurrence matrix (CLCM) and grey-level co-occurrence matrix (GLCM) are applied on both RGB and grey images. The extracted features are extracted using the wrapper method and the unsupervised dimension reduction technique namely independent component analysis (ICA) is used to reduce the dimension of extracted features. Afterward, the deep learning-based Ghost network is used for classifying normal, Mild TR, and severe TR cases. The classified TR cases are fed to the segmentation phase for segmenting the affected valve of the fetus. The experimental TRI-FH approach achieves a total accuracy of 98.07 %. As compared to existing techniques, the proposed TRI-FH method shows higher performance in terms of accuracy, precision, recall, specificity, and F1 score. The proposed TRI-FH model enhances the total accuracy by 95.64 %, 97.82 %, 93.21 %, and 95.67 % better than ResNet, DenseNet, LinkNet, and U-Net respectively.

Structure-aware preserving projections with applications to medical image clustering

The application of dimensionality reduction (DR) in effectively handling high-dimensional data is becoming increasingly prominent. However, mainstream methods in projection learning exhibit a reliance on either global or local structures, resulting in the inability to effectively learn the discriminative projection. To address this issue, we propose a novel unsupervised DR algorithm, called Structure-Aware Preserving Projections (SAPP). Specifically, SAPP exploits a powerful combination of subspace clustering and graph construction to effectively capture the intrinsic structure of the data. It is able to find discriminative projections, which is mainly attributed to two key factors: (1) can capture the local structure of the data by constructing the nearest neighbor graph and introducing the grouping effect of the representation into projection learning; and (2) preserves the global structure and respects the complex relationship between data points by integrating least squares regression into the dimension reduction process. Moreover, SAPP proves to be a versatile framework that is easily extended to semi-supervised scenarios. Extensive experiments on medical image datasets confirm the effectiveness of our proposed method, showcasing superior clustering accuracy compared to state-of-the-art approaches.

Stochastic and multi-objective design of photonic devices with machine learning

Compact and highly performing photonic devices are characterized by non-intuitive geometries, a large number of parameters, and multiple figures of merit. Optimization and machine learning techniques have been explored to handle these complex designs, but the existing approaches often overlook stochastic quantities. As an example, random fabrication uncertainties critically determines experimental device performance. Here, we present a novel approach for the stochastic multi-objective design of photonic devices combining unsupervised dimensionality reduction and Gaussian process regression. The proposed approach allows to efficiently identify promising alternative designs and model the statistic of their response. Incorporating both deterministic and stochastic quantities into the design process enables a comprehensive analysis of the device and of the possible trade-offs between different performance metrics. As a proof-of-concept, we investigate surface gratings for fiber coupling in a silicon-on-insulator platform, considering variability in structure sizes, silicon thickness, and multi-step etch alignment. We analyze 86 alternative designs presenting comparable performance when neglecting variability, discovering on the contrary marked differences in yield and worst-case figures for both fiber coupling efficiency and back-reflections. Pareto frontiers demonstrating optimized device robustness are identified as well, offering a powerful tool for the design and optimization of photonic devices with stochastic figures of merit.

Machine learning analysis of bleeding status in venous thromboembolism patients

BackgroundAnticoagulation therapy is the mainstay of therapy for patients with venous thromboembolism (VTE). However, continuing or stopping anticoagulants after the first 3 to 6 months is a difficult decision that requires ascertainment of the risk of bleeding and recurrent VTE. Despite the development of several statistical models to predict bleeding, the benefit of machine learning (ML) models has not been investigated in depth. ObjectivesTo assess the benefits of ML algorithms in bleeding risk evaluation in VTE patients and gain insight into their baseline information. MethodsThe baseline clinical, demographic, and genotype information was collected for 2542 patients with VTE who were on extended anticoagulation therapy. Six unsupervised dimensionality reduction and clustering ML algorithms were used to visualize and cluster the data for patients with major bleeding (118 patients) and nonbleeders. Eight supervised ML algorithms were trained and compared with the previously derived clinical models using a 5-fold nested cross-validation scheme. ResultsThe baseline dataset for bleeders and nonbleeders showed a high degree of similarity. Two novel clusters were discovered within the dataset for bleeders based on the presence of isolated pulmonary embolism or isolated deep vein thrombosis, though the difference in bleeding risks was not statistically significant (P = .32). The supervised analysis showed that the ML and clinical models have similar discrimination (c-statistics, ∼62%) and calibration performance (Brier score, ∼0.045). ConclusionThe clinical variables recorded at baseline are not distinctive enough to improve bleeding prediction beyond the performance of the existing models, and other strategies or data modalities should be considered.

MAGIC-DR: An interpretable machine-learning guided approach for acute myeloid leukemia measurable residual disease analysis.

Multiparameter flow cytometry is widely used for acute myeloid leukemia minimal residual disease testing (AML MRD) but is time consuming and demands substantial expertise. Machine learning offers potential advancements in accuracy and efficiency, but has yet to be widely adopted for this application. To explore this, we trained single cell XGBoost classifiers from 98 diagnostic AML cell populations and 30 MRD negative samples. Performance was assessed by cross-validation. Predictions were integrated with UMAP as a heatmap parameter for an augmented/interactive AML MRD analysis framework, which was benchmarked against traditional MRD analysis for 25 test cases. The results showed that XGBoost achieved a median AUC of 0.97, effectively distinguishing diverse AML cell populations from normal cells. When integrated with UMAP, the classifiers highlighted MRD populations against the background of normal events. Our pipeline, MAGIC-DR, incorporated classifier predictions and UMAP into flow cytometry standard (FCS) files. This enabled a human-in-the-loop machine learning guided MRD workflow. Validation against conventional analysis for 25 MRD samples showed 100% concordance in myeloid blast detection, with MAGIC-DR also identifying several immature monocytic populations not readily found by conventional analysis. In conclusion, Integrating a supervised classifier with unsupervised dimension reduction offers a robust method for AML MRD analysis that can be seamlessly integrated into conventional workflows. Our approach can support and augment human analysis by highlighting abnormal populations that can be gated on for quantification and further assessment. This has the potential to speed up MRD analysis, and potentially improve detection sensitivity for certain AML immunophenotypes.

Machine Learning Deciphered Molecular Mechanistics with Accurate Kinetic and Thermodynamic Prediction.

Time-lagged independent component analysis (tICA) and the Markov state model (MSM) have been extensively employed for extracting conformational dynamics and kinetic community networks from unbiased trajectory ensembles. However, these techniques may not be the optimal choice for elucidating transition mechanisms within low-dimensional representations, especially for intricate biosystems. Unraveling the association mechanism in such complex systems always necessitates permutations of several essential independent components or collective variables, a process that is inherently obscure and may require empirical knowledge for selection. To address these challenges, we have implemented an integrated unsupervised dimension reduction model: uniform manifold approximation and projection (UMAP) with hierarchy density-based spatial clustering of applications with noise (HDBSCAN). This approach effectively generates low-dimensional configurational embeddings. The hierarchical application of this architecture, in conjunction with MSM, reveals global kinetic connectivity while identifying local conformational states. Consequently, our methodology establishes a multiscale mechanistic elucidation framework. Leveraging the benefits of the uniform sample distribution and a denoising approach, our model demonstrates robustness in preserving global and local data structures compared to traditional dimension reduction methods in the field of MD analysis area. The interpretability of hyperparameter selection and compatibility with downstream tasks are cross-validated across various simulation data sets, utilizing both computational evaluation metrics and experimental kinetic observables. Furthermore, the predicted Mcl1-BH3 association kinetics (0.76 s-1) is in close agreement with surface plasmon resonance experiments (0.12 s-1), affirming the plausibility of the identified pathway composed of representative conformations. We anticipate that the devised workflow will serve as a foundational framework for studying recognition patterns in complex biological systems. Its contributions extend to the exploration of protein functional dynamics and rational drug design, offering a potent avenue for advancing research in these domains.

Tracking element-mineral associations with unsupervised learning and dimensionality reduction in chemical and optical image stacks of thin sections

In-situ chemical analysis on thin sections is a cornerstone of geochemical research. Despite massive advances in digital image analysis, the interpretation of such data within the optical petrological context of the thin section has largely remained an analogue task in geochemistry. In this contribution, we registered optical and micro-chemical images from large thin section areas. Chemical datasets from scanning electron microscopy energy dispersive spectrometry (SEM-EDX) and Synchrotron X-ray fluorescence microscopy (S-XFM) were exported from proprietary software. We then evaluated two dimensionality reduction techniques against false-colour images and phase maps to test whether previously unnoticed features became discoverable. Principal component analysis (PCA) and deep sparse autoencoder (DSA) neural networks were used to summarise the multi-channel SEM-EDX and S-XFM into one single red-green-blue (RGB) representation each.Applied to an oceanic gabbro, a cratonic peridotite, and a pelagic limestone, the PCA-based dimensionality reduction was found to produce crisp RGB maps of phases with less noise than false-colour three-element RGB maps. They were registered with optical images to form a simple multi-channel input for pixel-based classification into classes (i.e., semantic segmentation). This was fast and worked well for typical igneous and metamorphic rocks (1–3 h routine). In the chemically quite homogenous limestone, the combined optical and S-XFM PCA input was successfully classified into many phases that were unclassifiable on the conventional SEM-EDX phase map. From the segmented optical and S-XFM PCA map, we exported pixel locations of classified accessory phases back into the original proprietary S-XFM software. This allowed quantification of trace elements whose X-ray peaks were invisible in the original S-XFM quantification.The DSA-based approach yielded phase maps with greater noise, but the technique was very strong at detecting subtle features. In the gabbro sample, the DSA image identified cryptic relict cores in clinopyroxene more clearly than in the previously used Cr concentration map. A DSA training set can be obtained on a small ROI to generate a consistent large area DSA image from which more fragmental cores were observed. For a ROI on the gabbro thin section, the DSA representation map and the blended optical image were segmented and inspected with a loupe tool. This allowed us to generate interactive histograms and bin-scatter concentration plots of selected phases and to search for co-variations of element concentrations. This approach can be expanded to include data from any in situ geochemical acquisition tools and may help discover previously unseen features in complex elemental imagery.

Is Unsupervised Dimensionality Reduction Sufficient to Decode the Complexities of Electrochemical Impedance Spectra?

AbstractAs electrochemical research undergoes rapid technological progression, the acquisition of substantial amounts of electrochemical impedance spectra (EIS) becomes increasingly feasible. Yet, this advancement introduces intricate challenges in data processing, automation, and interpretation. This paper delves into the sufficiency of unsupervised machine learning (ML) and in particular dimensionality reduction methods in decoding EIS complexities, examining its strengths, limitations, and potential pathways for optimization. As we navigated the intricacies of non‐linear dimensionality reduction, spotlighting t‐distributed stochastic neighbor embedding (t‐SNE) and uniform manifold approximation and projection (UMAP) algorithms, a pattern emerged: these techniques excel at categorizing divergent impedance spectra but show limitations when faced with analogous circuit configurations, especially those substituting a capacitor with a constant phase element. This observation not only underscores a limitation but also accentuates that unsupervised ML approaches, alone, may not fully unravel the nuances of EIS spectra. In the concluding section of our manuscript, we discuss the implications of this finding from a practical standpoint, particularly for electrochemists seeking to apply these methods in their work.

Learning adaptive Grassmann neighbors for image-set analysis

Representing image sets as subspaces on Grassmann manifold and leveraging the Riemannian geometry of this space has proven to be highly effective in various visual recognition tasks. However, the computational cost associated with operating on Riemannian manifolds, especially of high-dimensional ones, poses a significant limitation to the applicability of existing techniques. Moreover, the image sets with labels are scarce and valuable in real-world scenarios, where the manual annotation is time-consuming and costly. To tackle these issues, in this paper, we propose an unsupervised Grassmannian dimensionality reduction method for image set classification and clustering, which simultaneously performs local structure learning and dimensionality reduction under the subspace view. Specifically, instead of relying on the pre-defined similarity matrix that obtained from raw data and may contain much noise, we adaptively learn the local structures from the projected low-dimensional Grassmann manifold. The refined structures then provide more discriminative power to learn the accurate manifold-to-manifold mapping. To better preserve the global structure of the data, this mapping is constrained to satisfy the orthogonal condition. In addition, our model can be compatible with F-norm OLPP for Grassmann manifold when the squared F-norm is transformed into projection metric. A re-weighted iterative scheme is carefully developed to optimize the problem. Experimental results on several benchmark datasets for image set classification and clustering tasks clearly demonstrate that our model consistently outperforms baselines, yielding significant improvements.

Unsupervised Dimensionality Reduction Modeling for Analyzing Aging Characteristics of Hanji

Unsupervised Dimensionality Reduction Modeling for Analyzing Aging Characteristics of Hanji

Transcriptional profiles of pulmonary artery endothelial cells in pulmonary hypertension

Pulmonary arterial hypertension (PAH) is characterized by endothelial cell (EC) dysfunction. There are no data from living patients to inform whether differential gene expression of pulmonary artery ECs (PAECs) can discern disease subtypes, progression and pathogenesis. We aimed to further validate our previously described method to propagate ECs from right heart catheter (RHC) balloon tips and to perform additional PAEC phenotyping. We performed bulk RNA sequencing of PAECs from RHC balloons. Using unsupervised dimensionality reduction and clustering we compared transcriptional signatures from PAH to controls and other forms of pulmonary hypertension. Select PAEC samples underwent single cell and population growth characterization and anoikis quantification. Fifty-four specimens were analyzed from 49 subjects. The transcriptome appeared stable over limited passages. Six genes involved in sex steroid signaling, metabolism, and oncogenesis were significantly upregulated in PAH subjects as compared to controls. Genes regulating BMP and Wnt signaling, oxidative stress and cellular metabolism were differentially expressed in PAH subjects. Changes in gene expression tracked with clinical events in PAH subjects with serial samples over time. Functional assays demonstrated enhanced replication competency and anoikis resistance. Our findings recapitulate fundamental biological processes of PAH and provide new evidence of a cancer-like phenotype in ECs from the central vasculature of PAH patients. This “cell biopsy” method may provide insight into patient and lung EC heterogeneity to advance precision medicine approaches in PAH.

New Insights into Hematopoietic Redefinition and New Paradigms in Hematopoietic Hierarchy Roadmap

The definition of hematopoietic progenitor cells (HPCs) has not been standardized. Surface markers are insufficient to capture the entire differentiation stages of progenitor cells and reflect the dynamic differentiation mechanisms underlying hematopoiesis. Deciphering the hematopoiesis mechanism that underlies progenitor cells definition and fate decision are critical to understanding fundamental questions of hematopoietic lineage commitment. Here, we redefined the entire spectrum of adult hematopoietic progenitors, and recovered the critical transcript factors (TFs) in lineages fate decision, and reaffirmed the lineage commitment model of HPCs by a comprehensive transcriptome. The progenitor lineages were accurately redefined with unique makers and transcription factors by unsupervised dimensionality reduction and clustering, which subverted the conventional definition of HPCs（Table 1）. The expression characteristics of TFs, such as GATA1, KLF1, PRDM1, and MAFB, presented enormous capacity to define the entire spectrum of HPCs. The transcriptional atlas showed that original hematopoietic progenitors were simultaneously primed into lymphoid, neutrophils, and megakaryocytic-erythroid progenitor cell types in the initial differentiation stage and thereafter matured into different hematopoietic lineages (Figure 1). The common intermediate progenitor stage was not observed among myeloid lineages, indicating the absence of a common myeloid progenitor during the lineage commitment. Our transcriptional atlas revealed the major fate decision factors in each branch among hematopoietic hierarchy formation (Table 1). Several fate decision factors were identified, including GATA2, TESPA1, and MYB of myeloid progenitors and HOXA9, HOPX, and TSC22D1 of lymphoid progenitors. Through the sequential activation/deactivation of TFs, synergism with key receptor genes, and signal activation, the original progenitor cells were primed and differentiated into various progenitors. The expression and activation characteristics of fate decision TFs faithfully reflect the mechanisms underlying hematopoietic lineage commitment. A hematopoietic hierarchy roadmap was reaffirmed. Our reaffirmed hematopoietic hierarchy validated that the megakaryocytic-erythroid lineage process is continuous, while the lymphoid lineage process is more likely a discrete stepwise progression with distinct lineage-committed populations during hematopoiesis, opening a new perspective on hematopoiesis (Figure 1). Our study revealed that the original progenitors of basophils, eosinophils, and neutrophils differed. Plasma progenitor cells were first identified and defined, and the rearrangements of IGHV, IGKV, and IGLV genes were already existed and occurred during the progenitor state of plasma cells. In summary, our transcriptional atlas of HPCs provides an accurate definition, hierarchy, and biological insights into hematopoiesis and lineage commitment. Our study opens up numerous possibilities for precise and controlled progenitor cell differentiation, facilitating research development in regenerative medicine and disease treatment.

Immune changes in hilar tumor draining lymph nodes following node sparing neoadjuvant chemoradiotherapy of localized cN0 non-small cell lung cancer

BackgroundWhile much progress has been accomplished in the understanding of radiation-induced immune effects in tumors, little is known regarding the mechanisms involved at the tumor draining lymph node (TDLN) level. The objective of this retrospective study was to assess the immune and biological changes arising in non-involved TDLNs upon node sparing concurrent chemoradiotherapy (CRT) of non-small cell lung cancer (NSCLC) tumors.MethodsPatients with proven localized (cN0M0) NSCLC, treated by radical surgery plus lymph node dissection with (CRT+) or without (CRT-) neoadjuvant chemoradiotherapy, whereby radiotherapy was targeted on the primary tumor with no significant incidental irradiation of the non-involved TDLN station (stations XI), were identified. Bulk RNA sequencing of TDLNs was performed and data were analyzed based on differential gene expression (DGE) and gene sets enrichment.ResultsSixteen patients were included and 25 TDLNs were analyzed: 6 patients in the CRT+ group (12 samples) and 10 patients in the CRT- group (13 samples). Overall, 1001 genes were differentially expressed between the two groups (CRT+ and CRT-). Analysis with g-profiler revealed that gene sets associated with antitumor immune response, inflammatory response, hypoxia, angiogenesis, epithelial mesenchymal transition and extra-cellular matrix remodeling were enriched in the CRT+ group, whereas only gene sets associated with B cells and B-cell receptor signaling were enriched in the CRT- group. Unsupervised dimensionality reduction identified two clusters of TDLNs from CRT+ patients, of which one cluster (cluster 1) exhibited higher expression of pathways identified as enriched in the overall CRT+ group in comparison to the CRT- group. In CRT+ cluster 1, 3 out of 3 patients had pathological complete response (pCR) or major pathological response (MPR) to neoadjuvant CRT, whereas only 1 out of 3 patients in the other CRT+ cluster (cluster 2) experienced MPR and none exhibited pCR.ConclusionNeoadjuvant node sparing concurrent CRT of NSCLC patients is associated with distinct microenvironment and immunological patterns in non-involved TDLNs as compared to non-involved TDLNs from patients with non-irradiated tumors. Our data are in line with studies showing superiority of lymph node sparing irradiation of the primary tumor in the induction of antitumor immunity.

Discrete Robust Principal Component Analysis via Binary Weights Self-Learning.

Principal component analysis (PCA) is a typical unsupervised dimensionality reduction algorithm, and one of its important weaknesses is that the squared l2 -norm cannot overcome the influence of outliers. Existing robust PCA methods based on paradigm have the following two drawbacks. First, the objective function of PCA based on the l1 -norm has no rotational invariance and limited robustness to outliers, and its solution mostly uses a greedy search strategy, which is expensive. Second, the robust PCA based on the l2,1 -norm and the l2,p -norm is essential to learn probability weights for data, which only weakens the influence of outliers on the learning projection matrix and cannot be completely eliminated. Moreover, the ability to detect anomalies is also very poor. To solve these problems, we propose a novel discrete robust principal component analysis (DRPCA). Through self-learning binary weights, the influence of outliers on the projection matrix and data center estimation can be completely eliminated, and anomaly detection can be directly performed. In addition, an alternating iterative optimization algorithm is designed to solve the proposed problem and realize the automatic update of binary weights. Finally, our proposed model is successfully applied to anomaly detection applications, and experimental results demonstrate that the superiority of our proposed method compared with the state-of-the-art methods.

A novel untrained SSVEP-EEG feature enhancement method using canonical correlation analysis and underdamped second-order stochastic resonance.

Compared with the light-flashing paradigm, the ring-shaped motion checkerboard patterns avoid uncomfortable flicker or brightness modulation, improving the practical interactivity of brain-computer interface (BCI) applications. However, due to fewer harmonic responses and more concentrated frequency energy elicited by the ring-shaped checkerboard patterns, the mainstream untrained algorithms such as canonical correlation analysis (CCA) and filter bank canonical correlation analysis (FBCCA) methods have poor recognition performance and low information transmission rate (ITR). To address this issue, a novel untrained SSVEP-EEG feature enhancement method using CCA and underdamped second-order stochastic resonance (USSR) is proposed to extract electroencephalogram (EEG) features. In contrast to typical unsupervised dimensionality reduction methods such as common average reference (CAR), principal component analysis (PCA), multidimensional scaling (MDS), and locally linear embedding (LLE), CCA exhibits higher adaptability for SSVEP rhythm components. This study recruits 42 subjects to evaluate the proposed method and experimental results show that the untrained method can achieve higher detection accuracy and robustness. This untrained method provides the possibility of applying a nonlinear model from one-dimensional signals to multi-dimensional signals.

Unsupervised Adaptive Bipartite Graph Embedding

In traditional graph embedding methods, graph construction is sensitive to high-dimensional data with noise and outliers, making an effective exploration of the neighborhood structure of the data difficult. Besides, with these methods, constructing graphs and reducing dimensions are disconnected and cannot be mutually optimized. To address these problems, we propose an unsupervised dimensionality reduction method based on bipartite graph, named unsupervised adaptive bipartite graph embedding (UABGE). First, the anchors are generated from the raw data by K-means or random sampling. Second, the bipartite graph, which is constructed between the samples and the anchors in the low-dimensional subspace, utilizes the adaptive allocation method to assign neighbors for each sample, so that the local structure of high-dimensional data can be captured effectively. Third, we present an objective function that combines bipartite graph construction and projection matrix learning to achieve mutual optimization between them, which can be solved with an alternating optimization algorithm. Finally, the computational complexity and the convergence of the algorithm are analyzed. Experimental results on synthetic data and publicly available datasets illustrate the effectiveness of the proposed method.

Dimensionality reduction methods for extracting functional networks from large-scale CRISPR screens.

CRISPR-Cas9 screens facilitate the discovery of gene functional relationships and phenotype-specific dependencies. The Cancer Dependency Map (DepMap) is the largest compendium of whole-genome CRISPR screens aimed at identifying cancer-specific genetic dependencies across human cell lines. A mitochondria-associated bias has been previously reported to mask signals for genes involved in other functions, and thus, methods for normalizing this dominant signal to improve co-essentiality networks are of interest. In this study, we explore three unsupervised dimensionality reduction methods-autoencoders, robust, and classical principal component analyses (PCA)-for normalizing the DepMap to improve functional networks extracted from these data. We propose a novel "onion" normalization technique to combine several normalized data layers into a single network. Benchmarking analyses reveal that robust PCA combined with onion normalization outperforms existing methods for normalizing the DepMap. Our work demonstrates the value of removing low-dimensional signals from the DepMap before constructing functional gene networks and provides generalizable dimensionality reduction-based normalization tools.